described in FIG. 1, etc. In some embodiments, the company may use a database or other source maintained by the company, while in other embodiments the server may access a database that is maintained by a third party. In some embodiments, the processor may also execute an instruction to order a virtual inspection on demand, if an image is not available. If a high resolution image for the structure is not available (NO branch of block 412), the processor may execute an instruction to end the method 400.

In some embodiments, the satellite image may fall within a certain time threshold. For example, the time threshold may be 72 hours, though other time thresholds may be used. This allows the underwriter to have access to recent data and make more accurate decisions. In some embodiments, the processor may execute one or more instructions to determine and/or confirm that the satellite image meets the time/quality threshold.

The processor may also execute an instruction to display the images (block 416). In some embodiments, rather than execute an instruction to display the image, the processor may execute an instruction to transmit the images to the client computing device for display. Once displayed, the underwriter may view the images and make any necessary decisions. The underwriter may input any action items based on the high resolution and/or satellite image. The processor executing the instruction may receive the action item (block 418) and link the action item to the customer account corresponding to the selected structure (block 420).

There are numerous action items and determinations which the underwriter may make using the presented system. Furthermore, the underwriter can view the images and determine certain objective and/or subjective categories. Objective categories may include whether the property in question is being used for a legal purpose and/or the purpose which the customer has claimed. Certain locations may be licensed for commercial activity, rental activity, etc. Other objective categories include number of stories of a structure, whether or not certain objects appear on the property or in the surrounding area, such as fire hydrants, garage, fences, pools, distance to coast, etc. The underwriter may also determine characteristic data corresponding to the objects. For example, the underwriter may determine the material that a roof is made out of or whether a pool is above ground or below ground. Subjective categories may include pride of ownership such as housekeeping, damage to one or more structures on the property (i.e. hail damage), whether there is a liability concern on the property or nearby, whether any part of the structure on the property is in need of repair.

FIG. 5 is a flow chart of a method, routine or process 500 for intelligent aerial image data analysis. As discussed above in reference to FIG. 4, during the underwriting process, an underwriter may determine one or more action items corresponding to a structure. In some embodiments, an automated processor for intelligent aerial image data analysis may be used to determine one or more action items. A processor of the server may execute an instruction to identify one or more object data categories from a retrieved image (block 502), such as the satellite image and/or high resolution image. The processor may further execute an instruction to determine one or more data values corresponding to the object data categories (block 504). The processor may also execute an instruction to identify one or more action items (block 506) based at least on the object data categories and/or data values and link the action item to the customer account (block 508). In some embodiments, the processor may also incorporate one or more business rules into the instruction. For example, a business rule may specify that if the structure includes a roof made of shingles, that an action item must be linked to a customer account. In some embodiments the processor may also execute an instruction to take one or more potential actions.

As a general example, the image retrieved may be of a structure such as a home. Accordingly, the processor may execute an instruction to analyze the image and translate the object data categories. Exemplary data categories include a roof, a pool, garage, fence, etc. Once the data category has been identified, the processor may execute an instruction to determine one or more object data values corresponding to the data category. In the roof example, the object data value may correspond to the roofing material and include, for example, shingles, slate, ceramic tile, copper, concrete, etc. Another value may correspond to a quality of the roof and/or roofing material and may be on a scale of 1-10, a percentage, or some other value. If the identified data category is a pool, the data values identified may be the type of pool, such as if the pool is in-ground, above ground, the approximate size of the pool, etc. The object data values may be objective data, such as whether an object data (such as a pool) is present, or a subjective value, describing the pool (in-ground, above ground, etc.). The object data categories and values may also be structured data retrieved from the image file, such as geocoded data, etc. Of course these are just examples and the data categories can be any of a wide variety of objects, etc. For example, if the structure is a commercial building, the object data categories may include a drive way, a parking garage, or other structure, fire hydrant, etc.

Turning briefly to FIG. 6, a sample aerial image 600 is provided. The processor executing the instructions may identify one or more object data categories, such as a house 602, a pool 604 and a garage 606. Of course these are just example object data categories and in some embodiments other data categories may be used. Furthermore, the processor executing the instructions may determine a data value for one of the identified object data categories. As one example, the processor executing the instruction may determine that data value for the pool 604, is that the pool is an in-ground pool. Of course this is just one example, and the methods provided can be used with any variety of aerial images, data values and data categories, etc.

FIG. 7 is a flow chart of a method, routine or process 700 for determining a best image data source. In some embodiments, multiple data sources for images may exist. For example, the server 112 may have access to one or more databases, including third party databases from multiple sources and/or one or more additional sources, such as the databases 116, 118, 126, 128, internet source 130, discussed in reference to FIG. 1. The processor may execute an instruction to determine the best data source (block 702). This may be done in a variety of ways. For example, the processor may execute an instruction to retrieve at least one image from each of the available data sources and to determine one of more characteristics of the image files retrieved, such as resolution, file format, etc. In some embodiments, one or more of the aerial image files and/or sources may be graded based on reliability or quality. In some embodiments, the server may store previous determinations and view the photos to execute an instruction to determine which is the best source available based on previous decisions.

Nonetheless, once the processor executing the instructions determines the best data source, the processor may execute an instruction to determine if the best data source is available for the desired structure (block 704). If the best data source is available for the desired structure, (YES branch of block 704), the processor may execute an instruction to retrieve one or more aerial images from the data source (block 706).

If the processor executing the instruction determines that the best data source is not available for the desired structure (NO branch of block 704), the processor may execute an instruction to select the next best data source (block 708) and determine whether the select data source is available for the structure (block 704). The processor may continue to execute instructions incorporating the method until a suitable source is found. In some embodiments, the processor may end the method 700 after a certain number of sources, certain amount of time, etc.

FIG. 8 is a flow chart of a method, routine or process 800 for determining if two or more objects in an image are within a threshold distance of each other. In some embodiments, an aerial image may have one or more relevant objects present. For example, in determining an insurance quote for a home, it may be relevant to the underwriter that the structures includes a pool in the backyard, a garage, a fence, a nearby fire hydrant, a nearby fire station, a nearby police station, home built on a slope or hilltop etc. The processor may execute an instruction to analyze the aerial image (block 802), identify a first object (block 804) and determine the location of the first object (block 806). The instruction executed by the processor may incorporate one or more image identifying techniques as are known on the art. The processor may further execute an instruction to identify a second object (block 808) and determine the location of the second object (block 810). In some embodiments, the first object and second object may correspond to one or more of the object data categories determined by the method 800, discussed above in reference to FIG. 8. Furthermore, although this discussion only mentions a first and a second object, those of ordinary skill in the art will recognize that the method 800 can involve any number of identified object data.

The processor may execute an instruction to determine a threshold distance (block 812), compare the locations of the first and second object (block 814) and determine if the locations meet the threshold distance (block 816). If the processor determines that the location meets the distance threshold, the processor executing the instruction may confirm the match (block 818). If the processor determines that the location does not meet the threshold distance, the processor executing the instruction may flag the customer account (block 820). In some embodiments, the processor may also use the confirmation to determine one or more answers for questions in the quote process and auto-populate a form corresponding to the quote process, such as an online form for an online quote process executing on a client device. The server may also execute an instruction to transmit the information to the client device for presentation, confirmation, etc.

For example, a processor of the server may execute an instruction incorporating the method 800 to determine if a fire station is within a threshold distance of a home. A customer may wish to receive a quote on a home insurance product, but a business rule may determine that a certain additional premium is to be charged if the customer's home is not within a threshold distance, for example five miles, of a fire station or determine the risk is unacceptable. Accordingly, the processor may execute an instruction to analyze the aerial image and identify a first object, such as the home structure itself. The processor may further execute an instruction to identify a second object, such as the fire station. The processor may then execute an instruction to compare the distances of the home structure and the fire station and determine whether or not the fire station is within the threshold distance of the home structure. Of course this is only an example for demonstration purposes, and the method 800 can be used with any variety of objects and/or threshold distances.

The following additional considerations apply to the foregoing discussion. Throughout this specification, plural instances may implement functions, components, operations, or structures described as a single instance. Although individual functions and instructions of one or more methods are illustrated and described as separate operations, one or more of the individual operations may be performed concurrently, and nothing requires that the operations be performed in the order illustrated. Structures and functionality presented as separate components in example configurations may be implemented as a combined structure or component. Similarly, structures and functionality presented as a single component may be implemented as separate components. These and other variations, modifications, additions, and improvements fall within the scope of the subject matter herein.

The methods described in this application may include one or more functions or routines in the form of non-transitory computer-executable instructions that are stored in a tangible computer-readable storage medium and executed using a processor of a computing device (e.g., the computing device 104, the server 112, or any combination of computing devices within the system 100). The routines may be included as part of any of the modules described in relation to FIG. 1 or 2 or as part of a module that is external to the system illustrated by FIGS. 1 and 2. For example, the methods may be part of a browser application or an application running on the computing device 104 as a plug-in or other module of the browser application. Further, the methods may be employed as “software-as-a-service” to provide a computing device 104 with access to the quote system 110.

Additionally, certain embodiments are described herein as including logic or a number of functions, components, modules, blocks, or mechanisms. Functions may constitute either software modules (e.g., non-transitory code stored on a tangible machine-readable storage medium) or hardware modules. A hardware module is a tangible unit capable of performing certain operations and may be configured or arranged in a certain manner. In example embodiments, one or more computer systems (e.g., a standalone, client or server computer system) or one or more hardware modules of a computer system (e.g., a processor or a group of processors) may be configured by software (e.g., an application or application portion) as a hardware module that operates to perform certain operations as described herein.

In various embodiments, a hardware module may be implemented mechanically or electronically. For example, a hardware module may comprise dedicated circuitry or logic that is permanently configured (e.g., as a special-purpose processor, such as a field programmable gate array (FPGA) or an application-specific integrated circuit (ASIC) to perform certain functions. A hardware module may also comprise programmable logic or circuitry (e.g., as encompassed within a general-purpose processor or other programmable processor) that is temporarily configured by software to perform certain operations. It will be appreciated that the decision to implement a hardware module mechanically, in dedicated and permanently configured circuitry, or in temporarily configured circuitry (e.g., configured by software) may be driven by cost and time considerations.